Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1229 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.0337. Min Range: -4.0337

Max Act: 4.0048. Min Act: -0.1699

Data Index: 491300 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 4.0337. Min Range: -4.0337

Max Act: 4.0337. Min Act: -0.1682

Data Index: 292151 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 4.0337. Min Range: -4.0337

Max Act: 4.0160. Min Act: -0.1700

Data Index: 762050 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 4.0337. Min Range: -4.0337

Max Act: 3.9832. Min Act: -0.1700

Data Index: 551196 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 4.0337. Min Range: -4.0337

Max Act: 3.9618. Min Act: -0.1700

Data Index: 1138798 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 4.0337. Min Range: -4.0337

Max Act: 3.9276. Min Act: -0.1678

Data Index: 331764 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 4.0337. Min Range: -4.0337

Max Act: 3.9052. Min Act: -0.1699

Data Index: 1235973 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 4.0337. Min Range: -4.0337

Max Act: 3.9023. Min Act: -0.1697

Data Index: 1156809 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 4.0337. Min Range: -4.0337

Max Act: 3.8823. Min Act: -0.1684

Data Index: 229205 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 4.0337. Min Range: -4.0337

Max Act: 3.8560. Min Act: -0.1695

Data Index: 975199 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 4.0337. Min Range: -4.0337

Max Act: 3.8236. Min Act: -0.1650

Data Index: 672385 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 4.0337. Min Range: -4.0337

Max Act: 3.8224. Min Act: -0.1699

Data Index: 822182 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 4.0337. Min Range: -4.0337

Max Act: 3.8323. Min Act: -0.1698

Data Index: 83422 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 4.0337. Min Range: -4.0337

Max Act: 3.8392. Min Act: -0.1641

Data Index: 825150 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 4.0337. Min Range: -4.0337

Max Act: 3.8550. Min Act: -0.1700

Data Index: 315529 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 4.0337. Min Range: -4.0337

Max Act: 3.8287. Min Act: -0.1696

Data Index: 840150 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 4.0337. Min Range: -4.0337

Max Act: 3.8428. Min Act: -0.1679

Data Index: 416734 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 4.0337. Min Range: -4.0337

Max Act: 3.8388. Min Act: -0.1692

Data Index: 422775 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 4.0337. Min Range: -4.0337

Max Act: 3.8557. Min Act: -0.1700

Data Index: 226089 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 4.0337. Min Range: -4.0337

Max Act: 3.8453. Min Act: -0.1669

Data Index: 704428 (C4 (Web Text))

Max Activating Token Index: 294